AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Jingkang Yang, Pengyun Wang, Dejian Zou, Zitang Zhou, Kunyuan Ding, WENXUAN PENG, Haoqi Wang, Guangyao Chen, Bo Li, Yiyou Sun, Xuefeng Du, Kaiyang Zhou and 4 more

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 84 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use simple data-augmentation methods such as PixMix instead of other evaluated method typesOOD detection · CIFAR-10 OOD benchmarkNear-OOD AUROC: 93.1%Improved
Use extra outlier data with UDG rather than the strongest data-free method, KNNOOD detection · CIFAR-10 near-OODAUROC: 91.9 vs 90.5Improved
Use extra outlier data with UDG rather than KNNOOD detection · CIFAR-100 OOD benchmarkAUROC: 75.8 vs 79.9Hurt
Use a post-hoc OOD method instead of a method requiring trainingOOD detection · generalized OOD detection benchmarksAUROCMixed
Apply data augmentation to improve uncertainty estimationOOD detection · CIFAR-10 and CIFAR-100 OOD benchmarksAUROC: 93.1%; 85.5%Improved
Use a detector evaluated on ImageNet instead of CIFAR benchmarksOOD detection · ImageNet, CIFAR-10, and CIFAR-100 OOD benchmarksAUROCMixed
Use recent KNN rather than classic MDSpost-hoc OOD detection · CIFAR-10 and CIFAR-100 OOD benchmarksAUROC: 90.5 vs 66.5; 79.9 vs 51.4Improved
Use anomaly-detection methods CutPaste or DRÆM for far-OOD detectionOOD detection · CIFAR-100 far-OODAUROC: 83.3; 85.4Improved
Use OSR methods for near-OOD detectionOOD detection · near-OOD benchmarksAUROCImproved
Use external outlier data for OOD trainingOOD detection · OOD detection benchmarksAUROCNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy